RE: AMD64 much slower than i386 on FreeBSD 5.4-pre
--- Subhro <[EMAIL PROTECTED]> wrote: > > > > -Original Message- > > From: [EMAIL PROTECTED] > [mailto:owner-freebsd- > > [EMAIL PROTECTED] On Behalf Of [EMAIL PROTECTED] > > Sent: Thursday, March 24, 2005 20:53 > > To: freebsd-questions@freebsd.org > > Subject: Re: AMD64 much slower than i386 on > FreeBSD 5.4-pre > > > > I think that warning people that the good name of > "FreeBSD" is being > > tainted by the current band of clowns is very > productive. Its more like > > a religion now; I've never seen so many people in > total denial that > > their > > > > OH NO!!! ANOTHER AOLer. > > One more entry added to my kill list. > > THIS IS MY EARNEST REQUEST TO ALL THE LIST MEMBERS. > BANDWIDTH IS VERY COSTLY > HERE SO PLEASE PLEASE PLEASE DO NOT WASTE BANDWIDTH > AND TIME BY FEEDING > TROLLS. You use gmail, so what bandwidth of yours is it using? Boris __ Do you Yahoo!? Yahoo! Small Business - Try our new resources site! http://smallbusiness.yahoo.com/resources/ ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: AMD64 much slower than i386 on FreeBSD 5.4-pre
I think you may be right. I try Broadcom gigE card with same results. Very slow for amd64 build. With same hardware, very good results with 4.9/i386, not too bad with 5.4-pre/i386, and very, very poor with 5.4-pre/amd64. Boris --- [EMAIL PROTECTED] wrote: > I think the point of a list is so that someone can > say "oh yes, I had > problems with the > em driver in amd64 also; try card X." But instead > you get a lot of > people with no real > idea trying to explain away the problem, as if there > is no chance that > the amd64 > implementant just plain sucks wind. If someone who > actually has an > amd64 build > could post some usage/load numbers, or someone who > did some testing > with > various hardware, that might be useful. So far what > we have is like a > bunch of > Mothers trying to defend their children without > having any viable > answers or > evidence than amd64 is any good at all. Only a > people who say > nonsensical > things like "my opteron blows away any P4", like a > kid bragging about > his > mustang or something. > > The em driver has a standard hold-off of 8000 > ints/second, so thats not > likely > the problem. Its likely to be the same in both i386 > and amd64, so its a > control. > > > > So the whole interrupt/process switching mechanism > runs like crap with > the amd64 build? Since I don't have a amd64 system, > and you might hav > access to atleast 1, how about getting a little info > on the irqs? Look > at systat -vmstat or vmstat -i under load? aybe > report it back? I > wonder if the irq rates are changing, or irqs are > taking longer to > service. Either there is a problem. Ofcourse some > hardware info would > be nice, chipset and cpu? Maybe you script vmstat -i > for a log, and use > netperf too? > I like Nick's followup. I would guese Boris may have > a problem with > proper hardware support. I can't really said it is > bad hardware if > speeds are the same, just high load(right?). Maybe > the driver he is > using is not good for 64bit as it is for 32bit? > > I think if Boris studies the thread I like to below > he will be alright. > > Check this out: > http://www.atm.tut.fi/list-archive/freebsd-stable/thrd66.html > http://docs.freebsd.org/cgi/mid.cgi?200502171636.10361.drice > > Inparticular: > http://www.atm.tut.fi/list-archive/freebsd-stable/msg19651.html > http://www.atm.tut.fi/list-archive/freebsd-stable/msg19679.html > ___ > freebsd-questions@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-questions > To unsubscribe, send any mail to > "[EMAIL PROTECTED]" > > > > ___ > freebsd-questions@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-questions > To unsubscribe, send any mail to > "[EMAIL PROTECTED]" > __ Do you Yahoo!? Make Yahoo! your home page http://www.yahoo.com/r/hs ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: AMD64 much slower than i386 on FreeBSD 5.4-pre
--- jason henson <[EMAIL PROTECTED]> wrote: > [EMAIL PROTECTED] wrote: > > > > > > >> The answer, Boris, is that the "team" has no idea > what > >> they're doing. Check out some of the threads on > >> performance testing. They tune little pieces here > > >> and there, and break 10 other things in the > process. > >> Matt Dillon "determined" that 10,000 ints/second > >> was "optimal". Of course if you're passing 10Kpps > > >> that means you get an interrupt for every > >> packet. > >> > >> They're playing pin the tail on the donkey. > >> > > > > You could understand what he was saying? I wanted > to help but was > > unsure of what he was asking. I also seem to > remember that discussion > > you are referring too. IIRC, 10,000hz for pooling > was the setting they > > ere talking about. But on it would very a little, > and with the fxp > > based card polling hurt a little because the card > was already ding its > > own thing in hardware. So that setting was > redundant, it was best to > > leave it alone. > > He also seemed to say the network bandwidth was > constant, and system > > load rose with an 64bit system. This right? If he > was using GENERIC on > > a smp system he was only using 1 cpu with out a > recompile. There is > > just so much that could be wrong and he gives no > information on his > > system or settings. > > Doess he have 2 amd64 pcs with 2 different > installs of 5.3, or a > > single machine that he ran both versions on? The > router, is that a > > third machine that was an amd64 system, or > something else? He says > > i386, but an up to date 5.3 world doesn't support > 386 with out a work > > around. The least commom setting is now 486, but a > build for 686 would > > be better. Did he tell you if he had polling on? > > > > So I guess it is a good thing you were able to > help him, because I > > couldn't. Not to mention the flame bait you > through out, well, that > > would be wrong. > ___ > > > > - Previous Message > > > > No, thats not what I was talking about. They were > tuning the MAX_INTS > > parameter for the em > > driver, which can hold off interrupts to reduce > system overhead. > > Instead of minimizing the load, > > they were focused on squeezing a few extra bits > out of iperf, which is > > not how you tune > > performance. If you get 700Kb/s and have a 95% > load and can get > > 695Kb/s with 60% load, > > which is better? Plus they were testing with a > regular PCI bus, so > > they were hitting the > > wall on the bus throughput, which changes all the > timings, so it was > > just a stupid test in > > general. > > > I would say 60% load. Now I completely understand > what you were saying. > > > > > I'm not 100% sure of what he was saying, but I've > seen the same thing. > > I take an i386 disk > > and pop on an amd64 disk with the same settings, > except for the 3 or 4 > > required differences, > > and the i386 machine has WAY less network load. So > maybe your > > buildworld runs faster, > > but the whole interrupt/process switching > mechanism runs like crap, so > > you likely have a > > slower machine. I haven't seen any test that shows > otherwise, just a > > bunch of swell > > guys swearing that one thing is faster than > another. > > > > I understand that you don't want to hear the > truth, so flame away. But > > its not going to make > > things any better. > > Ahh! More flame bait! I just didn't like you > platitudinal and > unproductive message that I believe would just drive > Boris onto linux > and leave a possible open problem on FreeBSD for > some one else to > discover latter. It's not that I don't want to hear > the truth, you were > just not saying anything worth his time. But > atleast now we can get > some where to help him and the amd64 port. I also > had the idea that > Boris was just trolling because he has not > responded, just said FreeBSD > was bad and left us to duke it out. > > > ___ > > freebsd-questions@freebsd.org mailing list > > > http://lists.freebsd.org/mailman/listinfo/freebsd-questions > > To unsubscribe, send any mail to > > "[EMAIL PROTECTED]" > > > So the whole interrupt/process switching mechanism > runs like crap with > the amd64 build? Since I don't have a amd64 system, > and you might hav > access to atleast 1, how about getting a little info > on the irqs? Look > at systat -vmstat or vmstat -i under load? aybe > report it back? I > wonder if the irq rates are changing, or irqs are > taking longer to > service. Either there is a problem. Ofcourse some > hardware info would > be nice, chipset and cpu? Maybe you script vmstat > -i for a log, and use > netperf too? > > I like Nick's followup. I would guese Boris may > have a problem with > proper hardware support. I can't really said it is > bad hardware if > speeds are the same, just high load(right?)
Re: AMD64 much slower than i386 on FreeBSD 5.4-pre
I think the point of a list is so that someone can say "oh yes, I had problems with the em driver in amd64 also; try card X." But instead you get a lot of people with no real idea trying to explain away the problem, as if there is no chance that the amd64 implementant just plain sucks wind. If someone who actually has an amd64 build could post some usage/load numbers, or someone who did some testing with various hardware, that might be useful. So far what we have is like a bunch of Mothers trying to defend their children without having any viable answers or evidence than amd64 is any good at all. Only a people who say nonsensical things like "my opteron blows away any P4", like a kid bragging about his mustang or something. The em driver has a standard hold-off of 8000 ints/second, so thats not likely the problem. Its likely to be the same in both i386 and amd64, so its a control. So the whole interrupt/process switching mechanism runs like crap with the amd64 build? Since I don't have a amd64 system, and you might hav access to atleast 1, how about getting a little info on the irqs? Look at systat -vmstat or vmstat -i under load? aybe report it back? I wonder if the irq rates are changing, or irqs are taking longer to service. Either there is a problem. Ofcourse some hardware info would be nice, chipset and cpu? Maybe you script vmstat -i for a log, and use netperf too? I like Nick's followup. I would guese Boris may have a problem with proper hardware support. I can't really said it is bad hardware if speeds are the same, just high load(right?). Maybe the driver he is using is not good for 64bit as it is for 32bit? I think if Boris studies the thread I like to below he will be alright. Check this out: http://www.atm.tut.fi/list-archive/freebsd-stable/thrd66.html http://docs.freebsd.org/cgi/mid.cgi?200502171636.10361.drice Inparticular: http://www.atm.tut.fi/list-archive/freebsd-stable/msg19651.html http://www.atm.tut.fi/list-archive/freebsd-stable/msg19679.html ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to "[EMAIL PROTECTED]" ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: AMD64 much slower than i386 on FreeBSD 5.4-pre
Maybe you shouldn't prejudge. Its clear than no one with their own addresses has any answers. -Original Message- From: Subhro <[EMAIL PROTECTED]> To: [EMAIL PROTECTED]; freebsd-questions@freebsd.org Sent: Thu, 24 Mar 2005 21:37:12 +0530 Subject: RE: AMD64 much slower than i386 on FreeBSD 5.4-pre -Original Message- From: [EMAIL PROTECTED] [mailto:owner-freebsd- [EMAIL PROTECTED] On Behalf Of [EMAIL PROTECTED] Sent: Thursday, March 24, 2005 20:53 To: freebsd-questions@freebsd.org Subject: Re: AMD64 much slower than i386 on FreeBSD 5.4-pre I think that warning people that the good name of "FreeBSD" is being tainted by the current band of clowns is very productive. Its more like a religion now; I've never seen so many people in total denial that their OH NO!!! ANOTHER AOLer. One more entry added to my kill list. THIS IS MY EARNEST REQUEST TO ALL THE LIST MEMBERS. BANDWIDTH IS VERY COSTLY HERE SO PLEASE PLEASE PLEASE DO NOT WASTE BANDWIDTH AND TIME BY FEEDING TROLLS. Best Regards S. Indian Institute of Information Technology Subhro Sankha Kar Block AQ-13/1, Sector V Salt Lake City PIN 700091 India ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to "[EMAIL PROTECTED]"
RE: AMD64 much slower than i386 on FreeBSD 5.4-pre
> -Original Message- > From: [EMAIL PROTECTED] [mailto:owner-freebsd- > [EMAIL PROTECTED] On Behalf Of [EMAIL PROTECTED] > Sent: Thursday, March 24, 2005 20:53 > To: freebsd-questions@freebsd.org > Subject: Re: AMD64 much slower than i386 on FreeBSD 5.4-pre > > I think that warning people that the good name of "FreeBSD" is being > tainted by the current band of clowns is very productive. Its more like > a religion now; I've never seen so many people in total denial that > their OH NO!!! ANOTHER AOLer. One more entry added to my kill list. THIS IS MY EARNEST REQUEST TO ALL THE LIST MEMBERS. BANDWIDTH IS VERY COSTLY HERE SO PLEASE PLEASE PLEASE DO NOT WASTE BANDWIDTH AND TIME BY FEEDING TROLLS. Best Regards S. Indian Institute of Information Technology Subhro Sankha Kar Block AQ-13/1, Sector V Salt Lake City PIN 700091 India smime.p7s Description: S/MIME cryptographic signature
Re: AMD64 much slower than i386 on FreeBSD 5.4-pre
I think that warning people that the good name of "FreeBSD" is being tainted by the current band of clowns is very productive. Its more like a religion now; I've never seen so many people in total denial that their beliefs are completely wrong. A lot of people are wasting a lot of time because of this propaganda. The cluelessness in the performance list is a good indication. -Original Message- From: jason henson <[EMAIL PROTECTED]> To: [EMAIL PROTECTED] Cc: freebsd-questions@freebsd.org; [EMAIL PROTECTED] Sent: Thu, 24 Mar 2005 00:57:58 -0500 Subject: Re: AMD64 much slower than i386 on FreeBSD 5.4-pre [EMAIL PROTECTED] wrote: > The answer, Boris, is that the "team" has no idea what >> they're doing. Check out some of the threads on >> performance testing. They tune little pieces here >> and there, and break 10 other things in the process. >> Matt Dillon "determined" that 10,000 ints/second >> was "optimal". Of course if you're passing 10Kpps >> that means you get an interrupt for every >> packet. >> >> They're playing pin the tail on the donkey. >> > You could understand what he was saying? I wanted to help but was > unsure of what he was asking. I also seem to remember that discussion > you are referring too. IIRC, 10,000hz for pooling was the setting they > ere talking about. But on it would very a little, and with the fxp > based card polling hurt a little because the card was already ding its > own thing in hardware. So that setting was redundant, it was best to > leave it alone. > He also seemed to say the network bandwidth was constant, and system > load rose with an 64bit system. This right? If he was using GENERIC on > a smp system he was only using 1 cpu with out a recompile. There is > just so much that could be wrong and he gives no information on his > system or settings. > Doess he have 2 amd64 pcs with 2 different installs of 5.3, or a > single machine that he ran both versions on? The router, is that a > third machine that was an amd64 system, or something else? He says > i386, but an up to date 5.3 world doesn't support 386 with out a work > around. The least commom setting is now 486, but a build for 686 would > be better. Did he tell you if he had polling on? > > So I guess it is a good thing you were able to help him, because I > couldn't. Not to mention the flame bait you through out, well, that > would be wrong. ___ > - Previous Message No, thats not what I was talking about. They were tuning the MAX_INTS parameter for the em driver, which can hold off interrupts to reduce system overhead. > Instead of minimizing the load, they were focused on squeezing a few extra bits out of iperf, which is > not how you tune performance. If you get 700Kb/s and have a 95% load and can get > 695Kb/s with 60% load, which is better? Plus they were testing with a regular PCI bus, so > they were hitting the wall on the bus throughput, which changes all the timings, so it was just a stupid test in general. I would say 60% load. Now I completely understand what you were saying. I'm not 100% sure of what he was saying, but I've seen the same thing. > I take an i386 disk and pop on an amd64 disk with the same settings, except for the 3 or 4 > required differences, and the i386 machine has WAY less network load. So maybe your > buildworld runs faster, but the whole interrupt/process switching mechanism runs like crap, so > you likely have a slower machine. I haven't seen any test that shows otherwise, just a bunch of swell guys swearing that one thing is faster than another. I understand that you don't want to hear the truth, so flame away. But > its not going to make things any better. Ahh! More flame bait! I just didn't like you platitudinal and unproductive message that I believe would just drive Boris onto linux and leave a possible open problem on FreeBSD for some one else to discover latter. It's not that I don't want to hear the truth, you were just not saying anything worth his time. But atleast now we can get some where to help him and the amd64 port. I also had the idea that Boris was just trolling because he has not responded, just said FreeBSD was bad and left us to duke it out. ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to > "[EMAIL PROTECTED]" So the whole interrupt/process switching mechanism runs like crap with the amd64 build? Since I don't have a amd64 system, and you might hav access to atleast 1, how about getting a littl
Re: AMD64 much slower than i386 on FreeBSD 5.4-pre
If you haven't used amd64 then why are you qualified to comment on the subject? If he's using the same settings for i386 and amd64, then the results should be balanced. I think the point here is that the same settings, which are probably the defaults, run a lot slower on amd64 than i386. And I don't see that you have any insight to provide. I hope FreeBSD hasn't become linux; in that it doesnt work out of the box and you have to selectively kludge it to show good results in any particular benchmark? Thats what made FreeBSD good historically. It was just good in general. -Original Message- From: Nick Pavlica <[EMAIL PROTECTED]> To: Boris Spirialitious <[EMAIL PROTECTED]> Cc: freebsd-questions@freebsd.org Sent: Wed, 23 Mar 2005 19:05:59 -0700 Subject: Re: AMD64 much slower than i386 on FreeBSD 5.4-pre Hi Boris, I haven't had an opportunity to work with any AMD64 hardware yet, but have had good results with 5.4.? on i686. I can relate to your frustration, but can say that I was able to greatly improve 5.x performance with some effort. For example I went from a maximum sustained disk write of 15Mb/s to 90Mb/s on a file server. That said, to help you get a better response to your question I would suggest trying these things: - Document and post your testing procedures and results. This will allow others to get a much clearer picture of what may be happening. As I'm sure you know support via e-mail is very difficult because there is so much information that is missing. - You may want to try the performance list if you don't get any answers from this list. - File a problem report so that the developers are aware of your situation. I don't think that they spend allot of time on this list. (http://www.freebsd.org/doc/en_US.ISO8859-1/articles/problem-reports/index.html) I hope this helps! --Nick What optimizations have you done to this point? ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to "[EMAIL PROTECTED]" ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: AMD64 much slower than i386 on FreeBSD 5.4-pre
[EMAIL PROTECTED] wrote: The answer, Boris, is that the "team" has no idea what they're doing. Check out some of the threads on performance testing. They tune little pieces here and there, and break 10 other things in the process. Matt Dillon "determined" that 10,000 ints/second was "optimal". Of course if you're passing 10Kpps that means you get an interrupt for every packet. They're playing pin the tail on the donkey. You could understand what he was saying? I wanted to help but was unsure of what he was asking. I also seem to remember that discussion you are referring too. IIRC, 10,000hz for pooling was the setting they ere talking about. But on it would very a little, and with the fxp based card polling hurt a little because the card was already ding its own thing in hardware. So that setting was redundant, it was best to leave it alone. He also seemed to say the network bandwidth was constant, and system load rose with an 64bit system. This right? If he was using GENERIC on a smp system he was only using 1 cpu with out a recompile. There is just so much that could be wrong and he gives no information on his system or settings. Doess he have 2 amd64 pcs with 2 different installs of 5.3, or a single machine that he ran both versions on? The router, is that a third machine that was an amd64 system, or something else? He says i386, but an up to date 5.3 world doesn't support 386 with out a work around. The least commom setting is now 486, but a build for 686 would be better. Did he tell you if he had polling on? So I guess it is a good thing you were able to help him, because I couldn't. Not to mention the flame bait you through out, well, that would be wrong. ___ - Previous Message No, thats not what I was talking about. They were tuning the MAX_INTS parameter for the em driver, which can hold off interrupts to reduce system overhead. Instead of minimizing the load, they were focused on squeezing a few extra bits out of iperf, which is not how you tune performance. If you get 700Kb/s and have a 95% load and can get 695Kb/s with 60% load, which is better? Plus they were testing with a regular PCI bus, so they were hitting the wall on the bus throughput, which changes all the timings, so it was just a stupid test in general. I would say 60% load. Now I completely understand what you were saying. I'm not 100% sure of what he was saying, but I've seen the same thing. I take an i386 disk and pop on an amd64 disk with the same settings, except for the 3 or 4 required differences, and the i386 machine has WAY less network load. So maybe your buildworld runs faster, but the whole interrupt/process switching mechanism runs like crap, so you likely have a slower machine. I haven't seen any test that shows otherwise, just a bunch of swell guys swearing that one thing is faster than another. I understand that you don't want to hear the truth, so flame away. But its not going to make things any better. Ahh! More flame bait! I just didn't like you platitudinal and unproductive message that I believe would just drive Boris onto linux and leave a possible open problem on FreeBSD for some one else to discover latter. It's not that I don't want to hear the truth, you were just not saying anything worth his time. But atleast now we can get some where to help him and the amd64 port. I also had the idea that Boris was just trolling because he has not responded, just said FreeBSD was bad and left us to duke it out. ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to "[EMAIL PROTECTED]" So the whole interrupt/process switching mechanism runs like crap with the amd64 build? Since I don't have a amd64 system, and you might hav access to atleast 1, how about getting a little info on the irqs? Look at systat -vmstat or vmstat -i under load? aybe report it back? I wonder if the irq rates are changing, or irqs are taking longer to service. Either there is a problem. Ofcourse some hardware info would be nice, chipset and cpu? Maybe you script vmstat -i for a log, and use netperf too? I like Nick's followup. I would guese Boris may have a problem with proper hardware support. I can't really said it is bad hardware if speeds are the same, just high load(right?). Maybe the driver he is using is not good for 64bit as it is for 32bit? I think if Boris studies the thread I like to below he will be alright. Check this out: http://www.atm.tut.fi/list-archive/freebsd-stable/thrd66.html http://docs.freebsd.org/cgi/mid.cgi?200502171636.10361.drice Inparticular: http://www.atm.tut.fi/list-archive/freebsd-stable/msg19651.html http://www.atm.tut.fi/list-archive/freebsd-stable/msg19679.html ___ freebsd-questions@freebsd.org mailin
Re: AMD64 much slower than i386 on FreeBSD 5.4-pre
Hi Boris, I haven't had an opportunity to work with any AMD64 hardware yet, but have had good results with 5.4.? on i686. I can relate to your frustration, but can say that I was able to greatly improve 5.x performance with some effort. For example I went from a maximum sustained disk write of 15Mb/s to 90Mb/s on a file server. That said, to help you get a better response to your question I would suggest trying these things: - Document and post your testing procedures and results. This will allow others to get a much clearer picture of what may be happening. As I'm sure you know support via e-mail is very difficult because there is so much information that is missing. - You may want to try the performance list if you don't get any answers from this list. - File a problem report so that the developers are aware of your situation. I don't think that they spend allot of time on this list. (http://www.freebsd.org/doc/en_US.ISO8859-1/articles/problem-reports/index.html) I hope this helps! --Nick What optimizations have you done to this point? ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: AMD64 much slower than i386 on FreeBSD 5.4-pre
The answer, Boris, is that the "team" has no idea what they're doing. Check out some of the threads on performance testing. They tune little pieces here and there, and break 10 other things in the process. Matt Dillon "determined" that 10,000 ints/second was "optimal". Of course if you're passing 10Kpps that means you get an interrupt for every packet. They're playing pin the tail on the donkey. You could understand what he was saying? I wanted to help but was unsure of what he was asking. I also seem to remember that discussion you are referring too. IIRC, 10,000hz for pooling was the setting they ere talking about. But on it would very a little, and with the fxp based card polling hurt a little because the card was already ding its own thing in hardware. So that setting was redundant, it was best to leave it alone. He also seemed to say the network bandwidth was constant, and system load rose with an 64bit system. This right? If he was using GENERIC on a smp system he was only using 1 cpu with out a recompile. There is just so much that could be wrong and he gives no information on his system or settings. Doess he have 2 amd64 pcs with 2 different installs of 5.3, or a single machine that he ran both versions on? The router, is that a third machine that was an amd64 system, or something else? He says i386, but an up to date 5.3 world doesn't support 386 with out a work around. The least commom setting is now 486, but a build for 686 would be better. Did he tell you if he had polling on? So I guess it is a good thing you were able to help him, because I couldn't. Not to mention the flame bait you through out, well, that would be wrong. ___ - Previous Message No, thats not what I was talking about. They were tuning the MAX_INTS parameter for the em driver, which can hold off interrupts to reduce system overhead. Instead of minimizing the load, they were focused on squeezing a few extra bits out of iperf, which is not how you tune performance. If you get 700Kb/s and have a 95% load and can get 695Kb/s with 60% load, which is better? Plus they were testing with a regular PCI bus, so they were hitting the wall on the bus throughput, which changes all the timings, so it was just a stupid test in general. I'm not 100% sure of what he was saying, but I've seen the same thing. I take an i386 disk and pop on an amd64 disk with the same settings, except for the 3 or 4 required differences, and the i386 machine has WAY less network load. So maybe your buildworld runs faster, but the whole interrupt/process switching mechanism runs like crap, so you likely have a slower machine. I haven't seen any test that shows otherwise, just a bunch of swell guys swearing that one thing is faster than another. I understand that you don't want to hear the truth, so flame away. But its not going to make things any better. ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: AMD64 much slower than i386 on FreeBSD 5.4-pre
[EMAIL PROTECTED] wrote: The answer, Boris, is that the "team" has no idea what they're doing. Check out some of the threads on performance testing. They tune little pieces here and there, and break 10 other things in the process. Matt Dillon "determined" that 10,000 ints/second was "optimal". Of course if you're passing 10Kpps that means you get an interrupt for every packet. They're playing pin the tail on the donkey. You could understand what he was saying? I wanted to help but was unsure of what he was asking. I also seem to remember that discussion you are referring too. IIRC, 10,000hz for pooling was the setting they ere talking about. But on it would very a little, and with the fxp based card polling hurt a little because the card was already ding its own thing in hardware. So that setting was redundant, it was best to leave it alone. He also seemed to say the network bandwidth was constant, and system load rose with an 64bit system. This right? If he was using GENERIC on a smp system he was only using 1 cpu with out a recompile. There is just so much that could be wrong and he gives no information on his system or settings. Doess he have 2 amd64 pcs with 2 different installs of 5.3, or a single machine that he ran both versions on? The router, is that a third machine that was an amd64 system, or something else? He says i386, but an up to date 5.3 world doesn't support 386 with out a work around. The least commom setting is now 486, but a build for 686 would be better. Did he tell you if he had polling on? So I guess it is a good thing you were able to help him, because I couldn't. Not to mention the flame bait you through out, well, that would be wrong. ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: AMD64 much slower than i386 on FreeBSD 5.4-pre
The answer, Boris, is that the "team" has no idea what they're doing. Check out some of the threads on performance testing. They tune little pieces here and there, and break 10 other things in the process. Matt Dillon "determined" that 10,000 ints/second was "optimal". Of course if you're passing 10Kpps that means you get an interrupt for every packet. They're playing pin the tail on the donkey. : Am Mittwoch, 23. März 2005 01:19 schrieb Boris Spirialitious: > -- Emanuel Strobl <[EMAIL PROTECTED]> wrote: > Am Mittwoch, 23. März 2005 00:38 schrieb Boris > > > Spirialitious: > > > I have opteron 246 system with 2 port intel em > > > card. We have test bed with about 200Kbs traffic > > > and we route through 5.3/i386 system. Load is > > > about 50%. With same settings, amd64 system run > > > with 85% load. How could be so slow? What tuning > > > extra is needed for amd64 kernels? > > > > 200kB/s sounds like misconfigured duplex/negotiation > > mode. > > But why don't you try FreeBSD 5.4-BETA1? Many > > performance improvements were > > achieved and stability is given in the -STABLE > > branch (BETA1 is a relese of > > FreeBSD 5-STABLE) > > I am sorry, I mean 200Mb/s. It is a controlled stream Unfortunately that's a not so uncommon result with em and 5.3. There are tuning methods but they won't give the big kick. Like mentioned, try 5.4 (BETA1), depending on your employment you'll see tremendous improvement, I don't have values handy nor can I confirm that for amd64, but you really wnat to try out, especially if this box isn't productive yet, which it isn't if I understood correctly. I am running 5.4-Pre now. Its the same. Everyone always say try new version, but it always the same. i compare em to em, only difference is amd64 vs i386. So amd64 O/S is this much slower than i386? So why anyone use? Is like nobody know what is going on with this OS. Before, people tell me Opteron on i386 no good. But now that I test, its much better than amd64. Why is there always excuse with FreeBSD 5? Always try next version. Always same slow result? Boris __ Do you Yahoo!? Make Yahoo! your home page http://www.yahoo.com/r/hs ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to "[EMAIL PROTECTED]" ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to "[EMAIL PROTECTED]"
AMD64 much slower than i386 on FreeBSD 5.4-pre
--- Emanuel Strobl <[EMAIL PROTECTED]> wrote: > Am Mittwoch, 23. März 2005 01:19 schrieb Boris > Spirialitious: > > -- Emanuel Strobl <[EMAIL PROTECTED]> wrote: > > Am Mittwoch, 23. März 2005 00:38 schrieb Boris > > > > > Spirialitious: > > > > I have opteron 246 system with 2 port intel em > > > > card. We have test bed with about 200Kbs > traffic > > > > and we route through 5.3/i386 system. Load is > > > > about 50%. With same settings, amd64 system > run > > > > with 85% load. How could be so slow? What > tuning > > > > extra is needed for amd64 kernels? > > > > > > 200kB/s sounds like misconfigured > duplex/negotiation > > > mode. > > > But why don't you try FreeBSD 5.4-BETA1? Many > > > performance improvements were > > > achieved and stability is given in the -STABLE > > > branch (BETA1 is a relese of > > > FreeBSD 5-STABLE) > > > > I am sorry, I mean 200Mb/s. It is a controlled > stream > > Unfortunately that's a not so uncommon result with > em and 5.3. There are > tuning methods but they won't give the big kick. > > Like mentioned, try 5.4 (BETA1), depending on your > employment you'll see > tremendous improvement, I don't have values handy > nor can I confirm that for > amd64, but you really wnat to try out, especially if > this box isn't > productive yet, which it isn't if I understood > correctly. I am running 5.4-Pre now. Its the same. Everyone always say try new version, but it always the same. i compare em to em, only difference is amd64 vs i386. So amd64 O/S is this much slower than i386? So why anyone use? Is like nobody know what is going on with this OS. Before, people tell me Opteron on i386 no good. But now that I test, its much better than amd64. Why is there always excuse with FreeBSD 5? Always try next version. Always same slow result? Boris __ Do you Yahoo!? Make Yahoo! your home page http://www.yahoo.com/r/hs ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to "[EMAIL PROTECTED]"
